Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B

The Saxo/Linkbricks-Horizon-AI-Korean-llama3.1-sft-dpo-70B is a 70 billion parameter Korean language model developed by Yunsung Ji (Saxo) of Linkbricks Horizon-AI. Fine-tuned from NousResearch/Meta-Llama-3.1-70B-Instruct using SFT and DPO, it incorporates Korean-Chinese-English-Japanese cross-training data and logical data to enhance multilingual understanding and complex Korean logical problem-solving. This model is particularly strengthened for high-level analysis of customer reviews, social postings, and coding tasks, supporting a 32768-token context window and tool calling.